The goal of the project¶

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

import numpy as np

from functools import reduce

import math

import datetime

from scipy import stats as st

import plotly.express as px

import plotly.graph_objects as go

import copy

data_ice = pd.read_csv('/datasets/games.csv')

data_ice.info()

data_ice.head()

display(data_ice.describe(include=['object']))

display(data_ice.describe())

data_ice.columns = data_ice.columns.str.lower()

​

display(data_ice.isnull().sum())

data_ice.dropna(subset=['year_of_release'], inplace=True)

data_ice['year_of_release'] = data_ice['year_of_release'].astype('int')

data = data_ice[data_ice['name'].isnull()]

data_ice.dropna(subset=['name'], inplace=True)

data_ice.shape[0]

data_ice['total_sales'] = data_ice['na_sales'] + data_ice['eu_sales'] + data_ice['jp_sales'] + data_ice['other_sales']

data_ice['total_sales'].describe()

data = data_ice[data_ice['rating'].isnull()]

display(data.head())

data_ice = data_ice.fillna(0)

data_ice.loc[data_ice['user_score'] == 'tbd', ['user_score']] = 0

data_ice['user_score'] = data_ice['user_score'].astype(float)

data_ice.describe()

data_pivot_by_years = data_ice.pivot_table(index='year_of_release', values='total_sales', aggfunc='sum')

data_pivot_by_years.columns=['total_sales']

barplot= sns.barplot(x=data_pivot_by_years.index, y=data_pivot_by_years['total_sales'])

barplot.set_xticklabels(barplot.get_xticklabels(), rotation=90)

plt.xlabel('Year of release')

plt.ylabel('Total sales')

plt.title('Total sales of video games by years, USD million')

​

plt.show()

data_pivot_by_platforms = data_ice.pivot_table(index='platform', values='total_sales', aggfunc='sum')

data_pivot_by_platforms.columns=['total_sales']

data_pivot_by_platforms = data_pivot_by_platforms.sort_values('total_sales', ascending=False)

barplot= sns.barplot(x=data_pivot_by_platforms.index, y=data_pivot_by_platforms['total_sales'])

barplot.set_xticklabels(barplot.get_xticklabels(), rotation=90)

plt.xlabel('Platform')

plt.ylabel('Total sales')

plt.title('Total sales of video games by platforms, USD million')

platform_ps2 = (

    data_ice

    .query('platform == "PS2"')

    .pivot_table(index='year_of_release', values='total_sales', aggfunc=['median', 'sum'])

)

​

platform_ps2.columns=['median_sales', 'total_sales']

​

barplot = sns.barplot(x=platform_ps2.index, y=platform_ps2['total_sales'])

barplot.set_xticklabels(barplot.get_xticklabels(), rotation=90)

plt.xlabel('Year of release')

plt.ylabel('Total sales')

plt.title('Total sales of video games by platform PS2, USD million')

plt.show()

platform_x360 = (

    data_ice

    .query('platform == "X360"')

    .pivot_table(index='year_of_release', values='total_sales', aggfunc=['sum'])

)

​

platform_x360.columns=['total_sales']

​

barplot = sns.barplot(x=platform_x360.index, y=platform_x360['total_sales'])

barplot.set_xticklabels(barplot.get_xticklabels(), rotation=90)

plt.xlabel('Year of release')

plt.ylabel('Total sales')

plt.title('Total sales of video games by platform X360, USD million')

plt.show()

platform_2015 = (

    data_ice

    .query('year_of_release == 2015')

    .pivot_table(index='platform', values='total_sales', aggfunc='sum')

)

​

platform_2015.columns=['total_sales']

platform_2015 = platform_2015.sort_values('total_sales', ascending=False)

​

barplot = sns.barplot(x=platform_2015.index, y=platform_2015['total_sales'])

barplot.set_xticklabels(barplot.get_xticklabels(), rotation=90)

plt.xlabel('Platforms')

plt.ylabel('Total sales')

plt.title('Total sales of video games in 2015, USD million')

plt.show()

platform_ps4 = (

    data_ice

    .query('platform == "PS4"')

    .pivot_table(index='year_of_release', values='total_sales', aggfunc=['sum'])

)

platform_ps4.columns=['total_sales']

​

platform_xone = (

    data_ice

    .query('platform == "XOne"')

    .pivot_table(index='year_of_release', values='total_sales', aggfunc=['sum'])

)

platform_xone.columns=['total_sales']

​

platform_3ds = (

    data_ice

    .query('platform == "3DS"')

    .pivot_table(index='year_of_release', values='total_sales', aggfunc=['sum'])

)

platform_3ds.columns=['total_sales']

bar_plots = [

    go.Bar(x=platform_ps2.index, y=platform_ps2['total_sales'], name='PS2'),

    go.Bar(x=platform_x360.index, y=platform_x360['total_sales'], name='X360'),

    go.Bar(x=platform_ps4.index, y=platform_ps4['total_sales'], name='PS4'),

    go.Bar(x=platform_xone.index, y=platform_xone['total_sales'], name='XOne'),

    go.Bar(x=platform_3ds.index, y=platform_3ds['total_sales'], name='3DS')

]

layout = go.Layout(

    title = go.layout.Title(text='Total sales of selected platforms', x=0.5),

    yaxis_title = 'Total sales',

    xaxis_tickmode = 'array',

    xaxis_ticktext = tuple(data_ice['year_of_release'].values)

)

fig = go.Figure(data=bar_plots, layout=layout)

fig.show()

data_ice_from_2011 = data_ice.loc[data_ice['year_of_release'] >= 2011]

data_group_by_platforms = data_ice_from_2011.sort_values(by = 'platform')

​

plt.figure(figsize = (10,8))

sns.boxplot(x='platform', y='total_sales', data=data_group_by_platforms)

plt.xlabel("Platform")

plt.ylabel("Total sales, USD million")

plt.title('The influence of the platform of video games on total sales')

​

data_group_by_platforms.shape[0]

def remove_outlier(df, col):

    q1 = df['total_sales'].quantile(0.25)

    q3 = df['total_sales'].quantile(0.75)

    iqr = q3 - q1

    lower_limit = q1 - (1.5*iqr)

    upper_limit = q3 + (1.5*iqr)

    out_df = df.loc[(df['total_sales'] > lower_limit) & (df['total_sales'] < upper_limit)]

    return out_df

data_group_by_platforms_true = remove_outlier(data_group_by_platforms, 'total_sales')

plt.figure(figsize = (10,8))

sns.boxplot(x='platform', y='total_sales', data=data_group_by_platforms_true)

plt.xlabel("Platform")

plt.ylabel("Total sales, USD million")

plt.title('The influence of the platform of video games on total sales')

​

data_group_by_platforms_true.shape[0]

import sys

import warnings

if not sys.warnoptions:

       warnings.simplefilter("ignore")

data_x360 = data_group_by_platforms[data_group_by_platforms['platform'] == 'X360']

data_x360.loc[data_x360['user_score'] == 'tbd', ['user_score']] = 0 

data_x360['user_score'] = data_x360['user_score'].astype(float)

display(data_x360.describe(include='object'))

fig = px.scatter_matrix(data_x360,

                       dimensions=["user_score", "critic_score", "total_sales"],

                       title="Scatter matrix correlation by scores and total sales on the platform X360"

                       )

fig.show()

​

​

corr_user_score = data_x360['user_score'].corr(data_x360['total_sales'])

corr_critic_score = data_x360['critic_score'].corr(data_x360['total_sales'])

print('The correlation coefficient between user scores and total sales:')

print(corr_user_score)

print('The correlation coefficient between critic scores and total sales:')

print(corr_critic_score)

data_games_by_genre = data_ice_from_2011.pivot_table(index='genre', values='total_sales', aggfunc=['mean', 'sum'])

data_games_by_genre.columns = ["mean_sales", "total_sales"]

data_games_by_genre = data_games_by_genre.sort_values(by='total_sales', ascending=False)

display(data_games_by_genre)

​

fig, ax = plt.subplots(figsize = (10, 10))

ax.pie(data_games_by_genre['total_sales'], labels=data_games_by_genre.index, wedgeprops=dict(width=0.5))

ax.set_title('Distribution of games by genre and total sales, 2011-2016')

​

na_platforms = (

    data_ice_from_2011

    .pivot_table(index='platform', values='na_sales', aggfunc=['sum'])

)

na_platforms.columns=['total_sales']

na_top5_platforms = na_platforms.nlargest(5, 'total_sales')

na_top5_platforms.sort_values('total_sales', ascending=False)

display(na_top5_platforms)

​

na_genres = (

    data_ice_from_2011

    .pivot_table(index='genre', values='na_sales', aggfunc=['sum'])

)

na_genres.columns=['total_sales']

na_top5_genres = na_genres.nlargest(5, 'total_sales')

na_top5_genres.sort_values('total_sales', ascending=False)

display(na_top5_genres)

eu_platforms = (

    data_ice_from_2011

    .pivot_table(index='platform', values='eu_sales', aggfunc=['sum'])

)

eu_platforms.columns=['total_sales']

eu_top5_platforms = eu_platforms.nlargest(5, 'total_sales')

eu_top5_platforms.sort_values('total_sales', ascending=False)

display(eu_top5_platforms)

​

eu_genres = (

    data_ice_from_2011

    .pivot_table(index='genre', values='eu_sales', aggfunc=['sum'])

)

eu_genres.columns=['total_sales']

eu_top5_genres = eu_genres.nlargest(5, 'total_sales')

eu_top5_genres.sort_values('total_sales', ascending=False)

display(eu_top5_genres)

jp_platforms = (

    data_ice_from_2011

    .pivot_table(index='platform', values='jp_sales', aggfunc=['sum'])

)

jp_platforms.columns=['total_sales']

jp_top5_platforms = jp_platforms.nlargest(5, 'total_sales')

jp_top5_platforms.sort_values('total_sales', ascending=False)

display(jp_top5_platforms)

​

jp_jenres = (

    data_ice_from_2011

    .pivot_table(index='genre', values='jp_sales', aggfunc=['sum'])

)

jp_jenres.columns=['total_sales']

jp_top5_genres = jp_jenres.nlargest(5, 'total_sales')

jp_top5_genres.sort_values('total_sales', ascending=False)

display(jp_top5_genres)

bar_plots_genre = [

    go.Bar(x=na_top5_genres.index, y=na_top5_genres['total_sales'], name='North America'),

    go.Bar(x=eu_top5_genres.index, y=eu_top5_genres['total_sales'], name='Europe'),

    go.Bar(x=jp_top5_genres.index, y=jp_top5_genres['total_sales'], name='Japan')

]

layout = go.Layout(

    title = go.layout.Title(text='Market shares of genres for each region', x=0.5),

    yaxis_title = 'Total sales',

    xaxis_tickmode = 'array',

    xaxis_ticktext = tuple(data_ice['year_of_release'].values),

    barmode='stack'

)

fig = go.Figure(data=bar_plots_genre, layout=layout)

fig.show()

test = copy.deepcopy(data_ice_from_2011)

xone_test = test[test['platform'].isin(['XOne'])]

pc_test = test[test['platform'].isin(['PC'])]

​

pivot_xone = xone_test.pivot_table(index='year_of_release', values='user_score', aggfunc='mean')

pivot_xone.columns=['user_score']

pivot_pc = pc_test.pivot_table(index='year_of_release', values='user_score', aggfunc='mean')

pivot_pc.columns=['user_score']

xone_pc = [pivot_xone, pivot_pc]

pivot_total = reduce(lambda  left,right: pd.merge(left,right,on='year_of_release',how='outer'), xone_pc)

pivot_total.columns = ['user_score_xone', 'user_score_pc']

display(pivot_total)

fig = go.Figure(data=[

    go.Bar(name='XBox One', x=pivot_total.index, y=pivot_total['user_score_xone']),

    go.Bar(name='PC', x=pivot_total.index, y=pivot_total['user_score_pc'])

])

fig.update_layout(barmode='group')

fig.show()

​

​

alpha = .05

​

results = st.ttest_ind(pivot_xone['user_score'], pivot_pc['user_score'])

​

print('p-value: ', results.pvalue)

​

if (results.pvalue < alpha):

    print("We reject the null hypothesis")

else:

    print("We can't reject the null hypothesis")

action_test = test[test['genre'].isin(['Action'])]

sports_test = test[test['genre'].isin(['Sports'])]

​

pivot_action = action_test.pivot_table(index='year_of_release', values='user_score', aggfunc='mean')

pivot_action.columns=['user_score']

pivot_sports = sports_test.pivot_table(index='year_of_release', values='user_score', aggfunc='mean')

pivot_sports.columns=['user_score']

​

action_sports = [pivot_action, pivot_sports]

pivot_total1 = reduce(lambda  left,right: pd.merge(left,right,on='year_of_release',how='outer'), action_sports)

pivot_total1.columns = ['user_score_action', 'user_score_sports']

display(pivot_total1)

fig = go.Figure(data=[

    go.Bar(name='Action', x=pivot_total1.index, y=pivot_total1['user_score_action']),

    go.Bar(name='Sports', x=pivot_total1.index, y=pivot_total1['user_score_sports'])

])

fig.update_layout(barmode='group')

fig.show()